Dogfood
This routes exploratory QA and bug hunting sessions for mobile apps through agent-device, a CLI that lets Claude control iOS and Android devices. It checks you have version 0.14.0 or newer, reads the built-in dogfood workflow from the CLI's help system, then loops through opening sessions, taking screenshots, exploring flows, and capturing evidence for each issue found. The allowed tools are locked down to just agent-device and its npx equivalent, so you won't accidentally approve unrelated commands. Use it when you want Claude to systematically poke around a mobile app and surface bugs or UX problems without writing formal test cases first. It's pure runtime testing, no source code analysis.
- skills.sh installs
- 4.1K
- GitHub stars
- 3.2K
- last updated
- Jul 14, 2026
Install
$ npx -y skills add callstackincubator/agent-device --skill dogfood --agent claude-codeInstalls into .claude/skills of the current project.
Files
Dogfood
Router for exploratory QA. Private setup before using this skill:
agent-device --version
If that fails, stop and tell the user to expose a trusted agent-device binary on PATH or approve an exact-version npm command. This skill intentionally keeps allowed tools restricted to agent-device and npx agent-device.
Require agent-device >= 0.14.0; older CLIs lack these help topics. If older, stop and tell the user to upgrade the trusted install or approve an exact-version npm command. Do not run npm install -g agent-device@latest or npx -y agent-device@latest autonomously, and do not include version/upgrade commands in final plans.
Read current CLI guidance:
agent-device help dogfood
Loop: open app -> snapshot -i + screenshot -> explore flows -> capture evidence per issue -> close (close --shutdown if your session booted a local simulator or emulator, unless the user asks to keep it running).
Target app is required; infer platform or ask. Findings must come from runtime behavior, not source reads. Let help dogfood provide exact report shape, evidence commands, and current workflow guidance.
Sponsors
Agent CaffeineSponsoredClose your lid, come back to finished work
SnugSponsoredThe clipboard manager for the AI eraPromote your product hereReach 125k+ visitors monthly
WaxSponsoredBlock anything with supervision, without erasing your iPhonePromote your product hereReach 125k+ visitors monthly
knobsSponsoredSee your site on any phone, any day, in any languageDetails
- Repository
- github.com/callstackincubator/agent-device
- Category
- AI & Agent Building
- First seen
- May 16, 2026
More from callstackincubator/agent-device
All 3Recommended
More AI & Agent Building
security-generate-security-sample-dataelastic/agent-skillsGenerate sample security events, attack scenarios, and synthetic alerts for Elastic Security. Use when demoing, populating dashboards, testing detection rules, 4.1Kskills.sh installs
command-creatorsoftaworks/agent-toolkitThis skill should be used when creating a Claude Code slash command. Use when users ask to "create a command", "make a slash command", "add a command", or want 4.1Kskills.sh installs
literature-reviewlingzhi227/agent-research-skillsConduct comprehensive literature reviews using multi-perspective dialogue simulation. Generate diverse expert personas, conduct grounded Q&A conversations, and 4.1Kskills.sh installs
transcribeopenai/skillsTranscribe audio files to text with optional diarization and known-speaker hints. Use when a user asks to transcribe speech from audio/video, extract text from 4Kskills.sh installsmeme-factorysoftaworks/agent-toolkitGenerate memes using the memegen.link API. Use when users request memes, want to add humor to content, or need visual aids for social media. Supports 100+ popul4Kskills.sh installsreducing-entropysoftaworks/agent-toolkitManual-only skill for minimizing total codebase size. Only activate when explicitly requested by user. Measures success by final code amount, not effort. Bias t4Kskills.sh installs